{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KKZQZ4KMCCEEFPQX2DAOERDZFY","short_pith_number":"pith:KKZQZ4KM","schema_version":"1.0","canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","source":{"kind":"arxiv","id":"2606.01599","version":1},"attestation_state":"computed","paper":{"title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingyuan Huang, Jin Sun, Ninghao Liu, Ruitong Sun, Tianze Yang, Yucheng Shi","submitted_at":"2026-06-01T02:52:49Z","abstract_excerpt":"Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, with fixed image-question-answer samples bounded by their collection budget. In this work, we introduce TRON (Targeted, Rule-verifiable Online eNvironments), an online environment substrate: a training rollout is generated on demand by a controllable generator-verifier program that samples a fresh latent visual state, renders an image, asks a question, and exactly verifies the answer. A single run can therefore draw "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T02:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"e0f889342c3be8fd9d9263e302198404d97460f51800e10fc3a468e91a266181","abstract_canon_sha256":"1f4e347e044f958571b492c1ac3efc313cc1ff87c59ef152a535948ea4cf5ef0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:37.669116Z","signature_b64":"PLMSqsjl8AHByBSmOcZ6W2OctgG8khLBeBcb1rlI6uRBTShI1dxCCSm7kXKKL4aFzK8KZWohh1dioJv7OvHSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","last_reissued_at":"2026-06-02T02:04:37.668691Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:37.668691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingyuan Huang, Jin Sun, Ninghao Liu, Ruitong Sun, Tianze Yang, Yucheng Shi","submitted_at":"2026-06-01T02:52:49Z","abstract_excerpt":"Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, with fixed image-question-answer samples bounded by their collection budget. In this work, we introduce TRON (Targeted, Rule-verifiable Online eNvironments), an online environment substrate: a training rollout is generated on demand by a controllable generator-verifier program that samples a fresh latent visual state, renders an image, asks a question, and exactly verifies the answer. A single run can therefore draw "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01599","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01599/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01599","created_at":"2026-06-02T02:04:37.668747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01599v1","created_at":"2026-06-02T02:04:37.668747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01599","created_at":"2026-06-02T02:04:37.668747+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKZQZ4KMCCEE","created_at":"2026-06-02T02:04:37.668747+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKZQZ4KMCCEEFPQX","created_at":"2026-06-02T02:04:37.668747+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKZQZ4KM","created_at":"2026-06-02T02:04:37.668747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY","json":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY.json","graph_json":"https://pith.science/api/pith-number/KKZQZ4KMCCEEFPQX2DAOERDZFY/graph.json","events_json":"https://pith.science/api/pith-number/KKZQZ4KMCCEEFPQX2DAOERDZFY/events.json","paper":"https://pith.science/paper/KKZQZ4KM"},"agent_actions":{"view_html":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY","download_json":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY.json","view_paper":"https://pith.science/paper/KKZQZ4KM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01599&json=true","fetch_graph":"https://pith.science/api/pith-number/KKZQZ4KMCCEEFPQX2DAOERDZFY/graph.json","fetch_events":"https://pith.science/api/pith-number/KKZQZ4KMCCEEFPQX2DAOERDZFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/action/storage_attestation","attest_author":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/action/author_attestation","sign_citation":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/action/citation_signature","submit_replication":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/action/replication_record"}},"created_at":"2026-06-02T02:04:37.668747+00:00","updated_at":"2026-06-02T02:04:37.668747+00:00"}